Security audit
Prompt Reviewer
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts describe repo-specific development and moderation workflows that are powerful but disclosed, scoped, and user-directed.
Install only if you expect repo-maintainer and Convex development automation. Review commands before running them, especially moderation, migration, PR publishing, package install, external-reviewer, and full-access nested review flows.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.